Search (91 results, page 1 of 5)

0.04997025 = product of:
  0.12492562 = sum of:
    0.07607185 = weight(_text_:index in 40) [ClassicSimilarity], result of:
      0.07607185 = score(doc=40,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.33795667 = fieldWeight in 40, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0546875 = fieldNorm(doc=40)
    0.04885377 = weight(_text_:22 in 40) [ClassicSimilarity], result of:
      0.04885377 = score(doc=40,freq=2.0), product of:
        0.18038483 = queryWeight, product of:
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.051511593 = queryNorm
        0.2708308 = fieldWeight in 40, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.0546875 = fieldNorm(doc=40)
  0.4 = coord(2/5)

Abstract

Conclusion There is a reason why Google Scholar and Web of Science/Scopus are kings of the hills in their various arenas. They have strong brand recogniton, a head start in development and a mass of eyeballs and users that leads to an almost virtious cycle of improvement. Competing against such well established competitors is not easy even when one has deep pockets (Microsoft) or a killer idea (scite). It will be interesting to see how the landscape will look like in 2030. Stay tuned for part II where I review each particular index.

Date

17.11.2020 12:22:59

0.04908844 = product of:
  0.2454422 = sum of:
    0.2454422 = weight(_text_:3a in 862) [ClassicSimilarity], result of:
      0.2454422 = score(doc=862,freq=2.0), product of:
        0.43671587 = queryWeight, product of:
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.051511593 = queryNorm
        0.56201804 = fieldWeight in 862, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          8.478011 = idf(docFreq=24, maxDocs=44218)
          0.046875 = fieldNorm(doc=862)
  0.2 = coord(1/5)

Source

https%3A%2F%2Farxiv.org%2Fabs%2F2212.06721&usg=AOvVaw3i_9pZm9y_dQWoHi6uv0EN

0.04283164 = product of:
  0.1070791 = sum of:
    0.06520444 = weight(_text_:index in 5620) [ClassicSimilarity], result of:
      0.06520444 = score(doc=5620,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.28967714 = fieldWeight in 5620, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=5620)
    0.04187466 = weight(_text_:22 in 5620) [ClassicSimilarity], result of:
      0.04187466 = score(doc=5620,freq=2.0), product of:
        0.18038483 = queryWeight, product of:
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.051511593 = queryNorm
        0.23214069 = fieldWeight in 5620, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.046875 = fieldNorm(doc=5620)
  0.4 = coord(2/5)

Abstract

There is a mutual resemblance between the behavior of users of the Stack Exchange and the dynamics of the citations accumulation process in the scientific community, which enabled us to tackle the outwardly intractable problem of assessing the impact of introducing "negative" citations. Although the most frequent reason to cite an article is to highlight the connection between the 2 publications, researchers sometimes mention an earlier work to cast a negative light. While computing citation-based scores, for instance, the h-index, information about the reason why an article was mentioned is neglected. Therefore, it can be questioned whether these indices describe scientific achievements accurately. In this article we shed insight into the problem of "negative" citations, analyzing data from Stack Exchange and, to draw more universal conclusions, we derive an approximation of citations scores. Here we show that the quantified influence of introducing negative citations is of lesser importance and that they could be used as an indicator of where the attention of the scientific community is allocated.

Date

6. 1.2020 18:10:22

0.035693035 = product of:
  0.08923259 = sum of:
    0.054337036 = weight(_text_:index in 885) [ClassicSimilarity], result of:
      0.054337036 = score(doc=885,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.24139762 = fieldWeight in 885, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0390625 = fieldNorm(doc=885)
    0.03489555 = weight(_text_:22 in 885) [ClassicSimilarity], result of:
      0.03489555 = score(doc=885,freq=2.0), product of:
        0.18038483 = queryWeight, product of:
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.051511593 = queryNorm
        0.19345059 = fieldWeight in 885, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.0390625 = fieldNorm(doc=885)
  0.4 = coord(2/5)

Abstract

MEDLINE is the National Library of Medicine's (NLM) journal citation database. It contains over 28 million references to biomedical and life science journal articles, and a key feature of the database is that all articles are indexed with NLM Medical Subject Headings (MeSH). The library employs a team of MeSH indexers, and in recent years they have been asked to index close to 1 million articles per year in order to keep MEDLINE up to date. An important part of the MEDLINE indexing process is the assignment of articles to indexers. High quality and timely indexing is only possible when articles are assigned to indexers with suitable expertise. This article introduces the NLM indexer assignment dataset: a large dataset of 4.2 million indexer article assignments for articles indexed between 2011 and 2019. The dataset is shown to be a valuable testbed for expert matching and assignment algorithms, and indexer article assignment is also found to be useful domain-adaptive pre-training for the closely related task of reviewer assignment.

Date

22. 1.2023 18:49:49

0.034020368 = product of:
  0.17010184 = sum of:
    0.17010184 = weight(_text_:index in 587) [ClassicSimilarity], result of:
      0.17010184 = score(doc=587,freq=10.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.75569415 = fieldWeight in 587, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0546875 = fieldNorm(doc=587)
  0.2 = coord(1/5)

Abstract

RILM Index is a partially controlled vocabulary designated to index scholarly writings on music and related subjects, created and curated by Répertoire International de Littérature Musicale (RILM). It has been developed over 50 years and has served the music community as a primary research tool. This analytical review of the characteristics of RILM Index reveals several issues, related to the Index's history, that impinge on its usefulness. An in-progress thesaurus is presented as a possible solution to these issues. RILM Index, despite being imperfect, provides a foundation for developing an ontological structure for both indexing and information retrieval purposes.

0.026081776 = product of:
  0.13040888 = sum of:
    0.13040888 = weight(_text_:index in 444) [ClassicSimilarity], result of:
      0.13040888 = score(doc=444,freq=8.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.5793543 = fieldWeight in 444, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=444)
  0.2 = coord(1/5)

Abstract

A citation index is a bibliographic database that provides citation links between documents. The first modern citation index was suggested by the researcher Eugene Garfield in 1955 and created by him in 1964, and it represents an important innovation to knowledge organization and information retrieval. This article describes citation indexes in general, considering the modern citation indexes, including Web of Science, Scopus, Google Scholar, Microsoft Academic, Crossref, Dimensions and some special citation indexes and predecessors to the modern citation index like Shepard's Citations. We present comparative studies of the major ones and survey theoretical problems related to the role of citation indexes as subject access points (SAP), recognizing the implications to knowledge organization and information retrieval. Finally, studies on citation behavior are presented and the influence of citation indexes on knowledge organization, information retrieval and the scientific information ecosystem is recognized.

Object

Science Citation Index

0.024590136 = product of:
  0.12295068 = sum of:
    0.12295068 = weight(_text_:index in 436) [ClassicSimilarity], result of:
      0.12295068 = score(doc=436,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.5462205 = fieldWeight in 436, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0625 = fieldNorm(doc=436)
  0.2 = coord(1/5)

Abstract

This paper discusses the use of wiki technology to provide a navigation structure for a collection of newspaper clippings. We overview the architecture of the wiki, discuss the navigation structure and pose the question: is the navigation structure an index, and if so, what type, or is it just a linkage structure or topic map. Does such a distinction really matter? Are these definitions in reality function based?

0.018442601 = product of:
  0.092213005 = sum of:
    0.092213005 = weight(_text_:index in 5676) [ClassicSimilarity], result of:
      0.092213005 = score(doc=5676,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.40966535 = fieldWeight in 5676, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=5676)
  0.2 = coord(1/5)

Abstract

This article offers an adjustment to the recently developed Euclidean Index (Perry and Reny, 2016). The proposed companion metric reflects the impact of the journal in which an article appears; the rationale for incorporating this information is to reflect higher costs of production and higher review standards, and to mitigate the heavily truncated citation counts that often arise in promotion, renewal, and tenure deliberations. Additionally, focusing jointly on citations and journal impact diversifies the assessment process, and can thereby help avoid misjudging scholars with modest citation counts in high-level journals. A combination of both metrics is also proposed, which nests each as a special case. The approach is demonstrated using a generic journal ranking metric, but can be adapted to most any stated or revealed preference measure of journal impact.

0.018442601 = product of:
  0.092213005 = sum of:
    0.092213005 = weight(_text_:index in 723) [ClassicSimilarity], result of:
      0.092213005 = score(doc=723,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.40966535 = fieldWeight in 723, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=723)
  0.2 = coord(1/5)

Abstract

Manual subject indexing in libraries is a time-consuming and costly process and the quality of the assigned subjects is affected by the cataloger's knowledge on the specific topics contained in the book. Trying to solve these issues, we exploited the opportunities arising from artificial intelligence to develop Kratt: a prototype of an automatic subject indexing tool. Kratt is able to subject index a book independent of its extent and genre with a set of keywords present in the Estonian Subject Thesaurus. It takes Kratt approximately one minute to subject index a book, outperforming humans 10-15 times. Although the resulting keywords were not considered satisfactory by the catalogers, the ratings of a small sample of regular library users showed more promise. We also argue that the results can be enhanced by including a bigger corpus for training the model and applying more careful preprocessing techniques.

0.018442601 = product of:
  0.092213005 = sum of:
    0.092213005 = weight(_text_:index in 1202) [ClassicSimilarity], result of:
      0.092213005 = score(doc=1202,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.40966535 = fieldWeight in 1202, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=1202)
  0.2 = coord(1/5)

Abstract

Collaboration across disciplines is a critical form of scientific collaboration to solve complex problems and make innovative contributions. This study focuses on the association between multidisciplinary collaboration measured by coauthorship in publications and the disruption of publications measured by the Disruption (D) index. We used authors' affiliations as a proxy of the disciplines to which they belong and categorized an article into multidisciplinary collaboration or monodisciplinary collaboration. The D index quantifies the extent to which a study disrupts its predecessors. We selected 13 journals that publish articles in six disciplines from the Microsoft Academic Graph (MAG) database and then constructed regression models with fixed effects and estimated the relationship between the variables. The findings show that articles with monodisciplinary collaboration are more disruptive than those with multidisciplinary collaboration. Furthermore, we uncovered the mechanism of how monodisciplinary collaboration disrupts science more than multidisciplinary collaboration by exploring the references of the sampled publications.

0.015368836 = product of:
  0.07684418 = sum of:
    0.07684418 = weight(_text_:index in 5982) [ClassicSimilarity], result of:
      0.07684418 = score(doc=5982,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.3413878 = fieldWeight in 5982, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5982)
  0.2 = coord(1/5)

Abstract

As the humanities develop in the realm of increasingly more pronounced digital scholarship, it is important to provide quality subject access to a vast range of heterogeneous information objects in digital services. The study aims to paint a representative picture of the current state of affairs of the use of subject index terms in humanities journal articles with particular reference to the well-established subject access needs of humanities researchers, with the purpose of identifying which improvements are needed in this context. Design/methodology/approach The comparison of subject metadata on a sample of 649 peer-reviewed journal articles from across the humanities is conducted in a university repository, against Scopus, the former reflecting local and national policies and the latter being the most comprehensive international abstract and citation database of research output. Findings The study shows that established bibliographic objectives to ensure subject access for humanities journal articles are not supported in either the world's largest commercial abstract and citation database Scopus or the local repository of a public university in Sweden. The indexing policies in the two services do not seem to address the needs of humanities scholars for highly granular subject index terms with appropriate facets; no controlled vocabularies for any humanities discipline are used whatsoever. Originality/value In all, not much has changed since 1990s when indexing for the humanities was shown to lag behind the sciences. The community of researchers and information professionals, today working together on digital humanities projects, as well as interdisciplinary research teams, should demand that their subject access needs be fulfilled, especially in commercial services like Scopus and discovery services.

0.015368836 = product of:
  0.07684418 = sum of:
    0.07684418 = weight(_text_:index in 1053) [ClassicSimilarity], result of:
      0.07684418 = score(doc=1053,freq=4.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.3413878 = fieldWeight in 1053, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1053)
  0.2 = coord(1/5)

Abstract

The quality of scientific publications can be measured by quantitative indices such as the h-index, Source Normalized Impact per Paper, or g-index. However, these measures lack to explain the function or reasons for citations and the context of citations from citing publication to cited publication. We argue that citation context may be considered while calculating the impact of research work. However, mining citation context from unstructured full-text publications is a challenging task. In this paper, we compiled a data set comprising 9,518 citations context. We developed a deep learning-based architecture for citation context classification. Unlike feature-based state-of-the-art models, our proposed focal-loss and class-weight-aware BiLSTM model with pretrained GloVe embedding vectors use citation context as input to outperform them in multiclass citation context classification tasks. Our model improves on the baseline state-of-the-art by achieving an F1 score of 0.80 with an accuracy of 0.81 for citation context classification. Moreover, we delve into the effects of using different word embeddings on the performance of the classification model and draw a comparison between fastText, GloVe, and spaCy pretrained word embeddings.

0.01395822 = product of:
  0.0697911 = sum of:
    0.0697911 = weight(_text_:22 in 1085) [ClassicSimilarity], result of:
      0.0697911 = score(doc=1085,freq=2.0), product of:
        0.18038483 = queryWeight, product of:
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.051511593 = queryNorm
        0.38690117 = fieldWeight in 1085, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.078125 = fieldNorm(doc=1085)
  0.2 = coord(1/5)

Date

18. 8.2022 19:22:57

0.013040888 = product of:
  0.06520444 = sum of:
    0.06520444 = weight(_text_:index in 5912) [ClassicSimilarity], result of:
      0.06520444 = score(doc=5912,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.28967714 = fieldWeight in 5912, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=5912)
  0.2 = coord(1/5)

Abstract

A search on the term "metadata" in the International Organization for Standardization's Online Browsing Platform (ISO OBP) reveals that there are 96 separate ISO standards that provide definitions of the term. Between them, these standards supply 46 different definitions-a lack of standardization that we might not have expected, given the context. In fact, if we make creative use of Simpson's index of concentration (originally devised as a measure of ecological diversity) to measure the degree of standardization of definition in this case, we arrive at a value of 0.05, on a scale of zero to one. It is suggested, however, that the situation is not as problematic as it might seem: that low cross-domain levels of standardization of definition should not be cause for concern.

0.013040888 = product of:
  0.06520444 = sum of:
    0.06520444 = weight(_text_:index in 586) [ClassicSimilarity], result of:
      0.06520444 = score(doc=586,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.28967714 = fieldWeight in 586, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=586)
  0.2 = coord(1/5)

Abstract

This article presents and discusses different kinds of data documents, including data sets, data studies, data papers and data journals. It provides descriptive and bibliometric data on different kinds of data documents and discusses the theoretical and philosophical problems by classifying documents according to the DIKW model (data documents, information documents, knowl­edge documents and wisdom documents). Data documents are, on the one hand, an established category today, even with its own data citation index (DCI). On the other hand, data documents have blurred boundaries in relation to other kinds of documents and seem sometimes to be understood from the problematic philosophical assumption that a datum can be understood as "a single, fixed truth, valid for everyone, everywhere, at all times".

0.013040888 = product of:
  0.06520444 = sum of:
    0.06520444 = weight(_text_:index in 591) [ClassicSimilarity], result of:
      0.06520444 = score(doc=591,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.28967714 = fieldWeight in 591, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=591)
  0.2 = coord(1/5)

Abstract

This article discusses the different meanings of 'keyword' and related terms such as 'keyphrase', 'descriptor', 'index term', 'subject heading', 'tag' and 'n-gram' and suggests definitions of each of these terms. It further illustrates a classification of keywords, based on how they are produced or who is the actor generating them and present comparison between author-assigned keywords, indexer-assigned keywords and reader-assigned keywords as well as the automatic generation of keywords. The article also considers the functions of keywords including the use of keywords for generating bibliographic indexes. The theoretical view informing the article is that the assignment of a keyword to a text, picture or other document involves an interpretation of the document and an evaluation of the document's potentials for users. This perspective is important for both manually assigned keywords and for automated generation and is opposed to a strong tendency to consider a set of keywords as ideally presenting one best representation of a document for all requests.

0.013040888 = product of:
  0.06520444 = sum of:
    0.06520444 = weight(_text_:index in 721) [ClassicSimilarity], result of:
      0.06520444 = score(doc=721,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.28967714 = fieldWeight in 721, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.046875 = fieldNorm(doc=721)
  0.2 = coord(1/5)

Abstract

The German National Library (DNB) is using a clustering technique to aggregate works from the database Culturegraph. Culturegraph collects bibliographic metadata records from all German Regional Library Networks, the Austrian Library Network, and DNB. This stock of about 180 million records serves as the basis for work clustering-the attempt to assemble all manifestations of a work in one cluster. The results of this work clustering are not employed in the display of search results, as other similar approaches successfully do, but for transferring metadata elements among the cluster members. In this paper the transfer of content-descriptive metadata elements such as controlled and uncontrolled index terms and classifications and links to name records in the German Integrated Authority File (GND) are described. In this way, standardization and cross linking can be improved and the richness of metadata description can be enhanced.

0.011166576 = product of:
  0.05583288 = sum of:
    0.05583288 = weight(_text_:22 in 5749) [ClassicSimilarity], result of:
      0.05583288 = score(doc=5749,freq=2.0), product of:
        0.18038483 = queryWeight, product of:
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.051511593 = queryNorm
        0.30952093 = fieldWeight in 5749, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.5018296 = idf(docFreq=3622, maxDocs=44218)
          0.0625 = fieldNorm(doc=5749)
  0.2 = coord(1/5)

Date

2. 3.2020 19:04:22

0.010867408 = product of:
  0.054337036 = sum of:
    0.054337036 = weight(_text_:index in 5512) [ClassicSimilarity], result of:
      0.054337036 = score(doc=5512,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.24139762 = fieldWeight in 5512, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5512)
  0.2 = coord(1/5)

Abstract

Web ad effect evaluation is a challenging problem in web marketing research. Although the analysis of web ad effectiveness has achieved excellent results, there are still some deficiencies. First, there is a lack of an in-depth study of the relevance between advertisements and web content. Second, there is not a thorough analysis of the impacts of users and advertising features on user browsing behaviors. And last, the evaluation index of the web advertisement effect is not adequate. Given the above problems, we conducted our work by studying the observer's behavioral pattern based on multimodal features. First, we analyze the correlation between ads and links with different searching results and further assess the influence of relevance on the observer's attention to web ads using eye-movement features. Then we investigate the user's behavioral sequence and propose the directional frequent-browsing pattern algorithm for mining the user's most commonly used browsing patterns. Finally, we offer the novel use of "memory" as a new measure of advertising effectiveness and further build an advertising memory model with integrated multimodal features for predicting the efficacy of web ads. A large number of experiments have proved the superiority of our method.

0.010867408 = product of:
  0.054337036 = sum of:
    0.054337036 = weight(_text_:index in 5732) [ClassicSimilarity], result of:
      0.054337036 = score(doc=5732,freq=2.0), product of:
        0.2250935 = queryWeight, product of:
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.051511593 = queryNorm
        0.24139762 = fieldWeight in 5732, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.369764 = idf(docFreq=1520, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5732)
  0.2 = coord(1/5)

Abstract

Recent technological developments have increased the use of machine learning to solve many problems, including many in information retrieval. Multimedia information retrieval as a problem represents a significant challenge to machine learning as a technological solution, but some problems can still be addressed by using appropriate AI techniques. We review the technological developments and provide a perspective on the use of machine learning in conjunction with knowledge organization to address multimedia IR needs. The semantic gap in multimedia IR remains a significant problem in the field, and solutions to them are many years off. However, new technological developments allow the use of knowledge organization and machine learning in multimedia search systems and services. Specifically, we argue that, the improvement of detection of some classes of lowlevel features in images music and video can be used in conjunction with knowledge organization to tag or label multimedia content for better retrieval performance. We provide an overview of the use of knowledge organization schemes in machine learning and make recommendations to information professionals on the use of this technology with knowledge organization techniques to solve multimedia IR problems. We introduce a five-step process model that extracts features from multimedia objects (Step 1) from both knowledge organization (Step 1a) and machine learning (Step 1b), merging them together (Step 2) to create an index of those multimedia objects (Step 3). We also overview further steps in creating an application to utilize the multimedia objects (Step 4) and maintaining and updating the database of features on those objects (Step 5).